© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257946
    Prev
    Next
    INDEX
    Explanations

    network connection or physical integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reachable
    0.31
     formative
    0.29
    动作
    0.28
     init
    0.28
     desenho
    0.28
     issu
    0.27
     sequence
    0.27
    {\'
    0.27
     progression
    0.27
     synced
    0.27
    POSITIVE LOGITS
     சரிய
    0.32
     oublier
    0.31
    sell
    0.30
    考える
    0.30
    дек
    0.29
    યોગ
    0.29
     вакци
    0.29
     ತಂಡ
    0.29
     высокая
    0.29
     যুগ্ম
    0.28
    Activations Density 0.007%

    No Known Activations